Journal of Cryptography and Network Security, Design and Codes

Cyber Emergency Intelligence & Response Coordination Platform

S. Santhosh — 2026-10-08

The study proposes a Cyber Emergency Intelligence and Response Coordination Platform, which is a central cybersecurity system created to identify, analyze, investigate, and coordinate responses to cyber incidents. The platform gathers cyber incident reports and security data from authorized network, Linux, and Windows systems into one place. It finds related incidents by linking data from many sources and gives a dynamic risk score so that security analysts can prioritize important incidents. A major feature is the Attack Path/Incident Explanation Engine, which studies available reports, logs, and security events and shows a possible sequence of how an incident might have happened. Every stage of that sequence can be tied to evidence or log data, which helps analysts see the incident more clearly. The platform also supports investigating incidents, preserving evidence with SHA-256 hashing, building incident timelines, and giving response recommendations. The recommended actions are approved by authorized security personnel before they are carried out. Once an incident is verified, the platform can produce privacy-preserving cyber-safety alerts for the public that do not reveal personal or organizational details. The platform can be deployed in the cloud and is built with DevOps/DevSecOps practices using Git, Docker, and automated deployment workflows. Network monitoring and authorized endpoint security data can be brought in with tools such as Wireshark, Nmap, Linux/Windows logs, and Wazuh. Overall, the platform brings together network security, endpoint monitoring, incident response, digital forensics, cloud computing, and DevSecOps into one system that does more than manage incidents; it also explains how incidents might have happened and gives security information to analysts and the public.

Smart Collaborative Coding Environment with AI Assistance: An Extensive Study

Bhumika A. R — 2026-08-20

Software development has evolved significantly with the rapid growth of cloud computing, remote work, and distributed software engineering, making real-time collaboration an essential requirement for modern development teams. Existing collaborative coding platforms provide synchronized code editing and communication facilities; however, many lack intelligent AI-powered features such as automated code review, context-aware programming assistance, code translation, coding activity analysis, and development replay. This survey presents a comprehensive review of recent research on collaborative coding environments, real-time synchronization techniques, Artificial Intelligence (AI)-assisted software development, and cloud-based code collaboration platforms. The study analyzes existing approaches, technologies, architectures, advantages, limitations, and research challenges in developing intelligent collaborative coding systems. Based on the identified research gaps, this survey highlights the need for an integrated Smart Collaborative Coding Environment with AI Assistance that combines real-time cursor tracking, an AI Chat Assistant, an AI Project Assistant, AI-powered code review, AI code translation, Code Replay, and a Coding Timeline within a single platform. These features aim to enhance collaboration, improve code quality, simplify debugging, support multilingual programming, visualize project evolution, and increase developer productivity.

Enhanced Medical Records Protection Using Quantum-Inspired Feature Optimization Based on AI-Driven Threat Detection with Tamper-Proof Blockchain Security

Shailendra Singh Tomar — 2026-09-28

The exponential growth of Electronic Medical Records (EMRs) has changed the way healthcare services are provided today by making it possible to monitor patients, diagnose illnesses, and make clinical decisions on a more effective basis than ever before. Unfortunately, the increased sharing of sensitive healthcare data across disparate environments has heightened concerns regarding confidentiality, integrity, unauthorized access, and cyberattacks. To help address these issues, an Intelligent Blockchain-Based Medical Records Protection Framework (IBMRPF) combines state-of-the-art feature optimization with deep analytics for detecting cyber threats and the inclusion of secure (tamper-proof) blockchain technology. The first phase of operation includes the acquisition and preprocessing of healthcare data using the MIMIC-III Clinical Database, Heart Disease UCI Dataset, and Diabetes 130-US Hospitals Dataset, which was accomplished using adaptive min-max normalization and data cleaning techniques. In addition, the new Quantum-Inspired Binary Enhanced Sparrow Search Optimization (QIBESSO) algorithm was developed to identify security-sensitive attributes related to healthcare and optimize the access-control features associated with them. The second phase of operation is centered on obtaining the security of the data through the use of a hybrid cryptographic protection layer constructed with Elliptic Curve Cryptography (ECC). This will allow for lightweight encryption and ensure fine-grained access control to the data provided to authorized entities within the healthcare industry. Finally, the third phase of operation is composed of a consortium blockchain that utilizes an Adaptive Quantum Swarm Consensus Algorithm (AQSCA) in order to provide immutable records of all transactions, provide a decentralized method for validating transactions, provide a secure mechanism for sharing data, and to protect against tampering of records. According to the findings of the validation study, the IBMRPF solution had a detection rate accuracy of 97.12%, precision of 97.86%, recall of 96.74%, and an F12 or F1 score of 95.80%, with a reduction in transaction validation time of 31.5%, encryption overhead of 28.7%, and computational cost of 26.9%. In addition, the throughput increased by 34.2%, and there was a 41.8% reduction in the number of unauthorized access events when compared to existing methods (Proof of Work and Proof of Authority) in healthcare security applications. By offering a scalable, automated, and private method for evolving healthcare ecosystems through secure management of electronic medical records and the sharing of reliable health information among distributed clinical environments.

ZeroDay Malware Identification in Cloud Virtual Machines Using Temporal Behavioral Features and Deep Ensemble Learning

Chandra Sekhar Koppireddy — 2026-09-30

Cloud computing has become an integral part of the way the modern organization runs. Cloud platforms are essential for businesses to store sensitive information, run applications, and provide large-scale services. The more that people start using the cloud, the more the risk of malware increases. Attackers have created new tools that are tailored to the cloud; many of these tools are not detected by traditional pattern- or signature-based tools. This paper presents a complete machine-learning-based malware detection system, which detects both known and unknown malware in cloud environments by analyzing malware behavior. The system tracks running processes and not specific patterns in the software. It continually gathers information on system calls, CPU usage, memory consumption, file system access, and network connections for virtual machines running on a private OpenStack cloud. These behavioral signals are then transformed into feature vectors and fed into three machine learning models: Random Forest, Support Vector Machine, and a Long Short-Term Memory neural network. Finally, the models make a classification decision by majority voting. The system was developed and evaluated using a set of 26,500 malware samples from five malware classes. The ensemble accurately classifies 98.7% of the cases, with a precision of 98.9% and a recall of 98.5%, while producing a very low false positive rate of 1.2%. The system also proves to be very good at generating zero-day threats, being able to identify previously unknown malware families over 89% accurately. The average detection latency is less than 400 milliseconds, and the processing overhead is less than 3% per VM. The findings in this work were validated and could be considered a reliable, scalable and feasible method for securing modern cloud environments using behavioral analysis and ensemble machine learning.